Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix issues with UTF-8 2-byte characters #938

Merged
merged 3 commits into from
Aug 7, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -1,9 +1,7 @@
package org.hl7.fhir.igtools.publisher;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.*;
import java.nio.charset.StandardCharsets;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
Expand Down Expand Up @@ -155,17 +153,17 @@ protected String getSushiCommandString(String fshVersion, Publisher.IGBuildMode

public static class MySushiHandler extends OutputStream {

private final StringBuilder buffer;
private final ByteArrayOutputStream buffer;
private int errorCount = -1;
private final Consumer<String> outputConsumer;

public MySushiHandler(final Consumer<String> outputConsumer) {
buffer = new StringBuilder(256);
buffer = new ByteArrayOutputStream(256);
this.outputConsumer = Objects.requireNonNull(outputConsumer);
}

public String getBufferString() {
return this.buffer.toString();
return this.buffer.toString(StandardCharsets.UTF_8);
}

private boolean passSushiFilter(String s) {
Expand All @@ -176,7 +174,11 @@ private boolean passSushiFilter(String s) {

@Override
public void write(int b) throws IOException {
this.buffer.appendCodePoint(b);
if (b >= -128 && b <= 127) {
this.buffer.write(b);
} else {
this.buffer.write('?');
}
if (b == 10) { // eoln
final String s = this.getBufferString();
if (passSushiFilter(s)) {
Expand All @@ -185,7 +187,7 @@ public void write(int b) throws IOException {
errorCount = Integer.parseInt(s.substring(10).trim());
}
}
this.buffer.setLength(0);
this.buffer.reset();
}
}

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,12 @@
import static org.junit.jupiter.api.Assertions.assertEquals;

import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.util.function.Consumer;

import javax.annotation.Nonnull;

import org.junit.jupiter.api.DisplayName;
import org.junit.jupiter.api.Test;

/**
Expand All @@ -21,8 +23,8 @@ void testMySushiHandler() throws IOException {

final StringBuilder stringBuilder = new StringBuilder(512);
final FSHRunner.MySushiHandler mySushiHandler = getMySushiHandler(stringBuilder);
for (final int codePoint : "1234".codePoints().toArray()) {
mySushiHandler.write(codePoint);
for (final int myByte : "1234".getBytes(StandardCharsets.UTF_8)) {
mySushiHandler.write(myByte);
}
assertEquals("1234", mySushiHandler.getBufferString());
assertEquals(0, stringBuilder.length());
Expand All @@ -31,6 +33,22 @@ void testMySushiHandler() throws IOException {
assertEquals("Sushi: 1234", stringBuilder.toString());
}

@Test
@DisplayName("Test MySushiHandler with UTF-8 two-byte characters")
void testMySushiHandlerTwoByte() throws IOException {

final StringBuilder stringBuilder = new StringBuilder(512);
final FSHRunner.MySushiHandler mySushiHandler = getMySushiHandler(stringBuilder);
for (final int myByte : "МЗРФ".getBytes(StandardCharsets.UTF_8)) {
mySushiHandler.write(myByte);
}
assertEquals("МЗРФ", mySushiHandler.getBufferString());
assertEquals(0, stringBuilder.length());
mySushiHandler.write(10); // EOL
assertEquals("", mySushiHandler.getBufferString());
assertEquals("Sushi: МЗРФ", stringBuilder.toString());
}

@Nonnull
private static FSHRunner.MySushiHandler getMySushiHandler(StringBuilder stringBuilder) {
final Consumer<String> stringConsumer = stringBuilder::append;
Expand Down
Loading